[ICLR2025] Kolmogorov-Arnold Transformer

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

This project is dedicated to the implementation and research of Kolmogorov-Arnold convolutional networks. The repository includes implementations of 1D, 2D, and 3D convolutions with different kernels, ResNet-like and DenseNet-like models, training code based on accelerate/PyTorch, as well as scripts for experiments with CIFAR-10 and Tiny ImageNet.

Residual Kolmogorov-Arnold Network (RKAN) is designed to enhance the performance of classic CNNs by incorporating RKAN blocks into existing architectures.

TKAN: Temporal Kolmogorov-Arnold Networks

Kolmogorov-Arnold Networks built on JAX

Improved LBFGS and LBFGS-B optimizers in PyTorch.

SigKAN: Signature-Weighted Kolmogorov-Arnold Networks for Time Series

This is the official repository for our paper KAGNNs: Kolmogorov-Arnold Networks meet Graph Learning.

FC-KAN: Function Combinations in Kolmogorov-Arnold Networks

Combine B-Splines (BS) and Radial Basis Functions (RBF) in Kolmogorov-Arnold Networks (KANs)

[ICASSP 2025] Official code of "Exploring Kolmogorov-Arnold networks for realistic image sharpness assessment"

All-KAN: All Kolmogorov-Arnold Networks We Know

Short experiment with Deep Q-Learning + KAN to play Flappy Bird.

Semi-supervised learning with Generative Adversarial Networks (GANs) using Kolmogorov-Arnold Network Layers (KANLs)

Code for Kolmogorov-Arnold Network for Quantum Architecture Search i.e., KANQAS

KANs for text classification on GLUE tasks

Python library designed to integrate Kolmogorov Arnold Networks with recurrent mechanisms.

X-KAN: Optimizing Local Kolmogorov-Arnold Networks via Evolutionary Rule-Based Machine Learning

This is the repo for the MixKABRN Neural Network (Mixture of Kolmogorov-Arnold Bit Retentive Networks), and an attempt at first adapting it for training on text, and later adjust it for other modalities.